© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59105
    Prev
    Next
    INDEX
    Explanations

    iques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bies
    1.20
    2
    1.17
    ম
    1.17
    ج
    1.16
    بو
    1.11
    IES
    1.10
     і
    1.09
    vit
    1.09
    kal
    1.09
    3
    1.08
    POSITIVE LOGITS
    '
    1.38
    ור
    1.36
    ти
    1.35
    ু
    1.20
    ות
    1.14
    ين
    1.13
    هي
    1.11
    ’
    1.09
    та
    1.07
    ление
    1.07
    Activations Density 0.001%

    No Known Activations